paper-with-me

홈 › Papers

LibContinual: A Comprehensive Library towards Realistic Continual Learning

2025-12-26 · Wenbin Li, Shangge Liu, Borui Kang, Yiyang Chen, KaXuan Lew, Yang Chen, Yinghuan Shi, Lei Wang, Yang Gao, Jiebo Luo arxiv

A fundamental challenge in Continual Learning (CL) is catastrophic forgetting, where adapting to new tasks degrades the performance on previous ones. While the field has evolved with diverse methods, this rapid surge in diverse methodologies has culminated in a fragmented research landscape. The lack of a unified framework, including inconsistent implementations, conflicting dependencies, and varying evaluation protocols, makes fair comparison and reproducible research increasingly difficult. To address this challenge, we propose LibContinual, a comprehensive and reproducible library designed to serve as a foundational platform for realistic CL. Built upon a high-cohesion, low-coupling modular architecture, LibContinual integrates 19 representative algorithms across five major methodological categories, providing a standardized execution environment. Meanwhile, leveraging this unified framework, we systematically identify and investigate three implicit assumptions prevalent in mainstream evaluation: (1) offline data accessibility, (2) unregulated memory resources, and (3) intra-task semantic homogeneity. We argue that these assumptions often overestimate the real-world applicability of CL methods. Through our comprehensive analysis using strict online CL settings, a novel unified memory budget protocol, and a proposed category-randomized setting, we reveal significant performance drops in many representative CL methods when subjected to these real-world constraints. Our study underscores the necessity of resource-aware and semantically robust CL strategies, and offers LibContinual as a foundational toolkit for future research in realistic continual learning. The source code is available from \href{https://github.com/RL-VIG/LibContinual}{https://github.com/RL-VIG/LibContinual}.

📄 PDF Abstract BibTeX arXiv:2512.22029

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

Avalanche RL: a Continual Reinforcement Learning Library

2022-02-28 · Nicolò Lucchesi, Antonio Carta, Vincenzo Lomonaco, Davide Bacciu

Continual Reinforcement Learning (CRL) is a challenging setting where an agent learns to interact with an environment that is constantly changing over time (the stream of experiences). In this paper, we describe Avalanch…

Continual LearningOpenAI Gymreinforcement-learningReinforcement Learning+1

Continual Inference: A Library for Efficient Online Inference with Deep Neural Networks in PyTorch

2022-04-07 · Lukas Hedegaard, Alexandros Iosifidis

We present Continual Inference, a Python library for implementing Continual Inference Networks (CINs) in PyTorch, a class of Neural Networks designed specifically for efficient inference in both online and batch processi…

MCITlib: Multimodal Continual Instruction Tuning Library and Benchmark

2025-08-10 · Haiyang Guo, Fei Zhu, Hongbo Zhao, Fanhu Zeng 외 arxiv

Continual learning enables AI systems to acquire new knowledge while retaining previously learned information. While traditional unimodal methods have made progress, the rise of Multimodal Large Language Models (MLLMs) b…

Continual Learning

Renate: A Library for Real-World Continual Learning

2023-04-24 · Martin Wistuba, Martin Ferianc, Lukas Balles, Cedric Archambeau 외

Continual learning enables the incremental training of machine learning models on non-stationary data streams.While academic interest in the topic is high, there is little indication of the use of state-of-the-art contin…

Continual Learning

Live and Learn: Continual Action Clustering with Incremental Views

2024-03-23 · Xiaoqiang Yan, Yingtao Gan, Yiqiao Mao, Yangdong Ye 외

Multi-view action clustering leverages the complementary information from different camera views to enhance the clustering performance. Although existing approaches have achieved significant progress, they assume all cam…

ClusteringContinual Learning